Image analysis to mine document information

Abstract

The present disclosure describes image analysis techniques that identify the source of a document. Once the source of the document is determined, the image analysis may locate one or more anchor fields in the document. The anchor fields may identify one or more additional fields that contain time-sensitive data and/or information. The image analysis performed herein may identify the time-sensitive data and/or information and process the data and/or information to schedule due dates and reminders.

What is claimed is: 
     
       1. A method comprising:
 obtaining, by a computing device, a document; 
 identifying, based on an automated analysis of the document, an anchor field; 
 identifying, based on the automated analysis of the document, a second field based on the second field being within a threshold distance of the anchor field, wherein the second field comprises time-sensitive information; 
 extracting and storing a plurality of details from the second field, wherein the plurality of details comprises an expiration date; 
 determining, using a radiodetermination mechanism, a location of the computing device; and 
 sending, based on a determination that the location of the computing device is associated with a merchant and based on a determination that the expiration date has not passed, a reminder of an offer associated with the time-sensitive information. 
 
     
     
       2. The method of  claim 1 , wherein the document comprises at least one of:
 a receipt; 
 a proof of purchase; or 
 an invoice. 
 
     
     
       3. The method of  claim 1 , wherein the obtaining the document comprises at least one of:
 capturing the document using an image capture device of the computing device; 
 importing the document from an email account; or 
 importing the document from a text message. 
 
     
     
       4. The method of  claim 1 , wherein the automated analysis of the document comprises at least one of natural language processing (NLP), object character recognition (OCR), or computer vision. 
     
     
       5. The method of  claim 1 , wherein the threshold distance comprises a predetermined number of pixels. 
     
     
       6. The method of  claim 1 , wherein the anchor field comprises a predetermined string of text. 
     
     
       7. The method of  claim 1 , wherein the second field comprises at least one of a barcode or a QR code. 
     
     
       8. The method of  claim 1 , wherein the offer comprises at least one of:
 a coupon; 
 a special offer; 
 a discount; 
 a reward; 
 a rebate; or 
 a survey. 
 
     
     
       9. The method of  claim 1 , further comprising:
 identifying a plurality of fields; 
 extracting one or more purchases from the plurality of fields; 
 categorizing each of the one or more purchases; 
 generating an expenditure report indicative of a user's spending habits, wherein the expenditure report comprises a category for each of the one or more purchases; and 
 causing the expenditure report to be presented on the computing device. 
 
     
     
       10. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform steps comprising:
 capturing, via an image capture device of a computing device, a document; 
 identifying, based on an automated analysis of the document, one or more fields, wherein at least one of the fields comprises a merchant identifier; 
 identifying a first field, of the one or more fields, as an anchor; 
 identifying a second field based on the second field being within a threshold distance of the anchor; 
 extracting a plurality of details from the second field; 
 storing the plurality of details, wherein the plurality of details comprises time-sensitive information; 
 determining, using a radiodetermination mechanism, a location of the computing device; and 
 sending, based on a determination that the location of the computing device is associated with the merchant identifier and based on a determination that the time-sensitive information has not expired, a reminder of an offer associated with the time-sensitive information. 
 
     
     
       11. The non-transitory computer-readable medium of  claim 10 , wherein the instructions, when executed by the one or more processors, cause the one or more processors to perform steps comprising:
 comparing the merchant identifier to a plurality of merchant identifiers stored in a database to determine a merchant associated with the merchant identifier. 
 
     
     
       12. The non-transitory computer-readable medium of  claim 10 , wherein the instructions, when executed by the one or more processors, cause the one or more processors to perform steps comprising:
 transmitting the merchant identifier to a server, wherein the server comprises a database storing a plurality of merchant identifiers; and 
 receiving, from the server, an indication of a merchant associated with the merchant identifier. 
 
     
     
       13. The non-transitory computer-readable medium of  claim 10 , wherein the reminder comprises at least one of: a text message, a push notification via a mobile app, or an email. 
     
     
       14. The non-transitory computer-readable medium of  claim 10 , wherein the instructions, when executed by the one or more processors, cause the one or more processors to perform steps comprising:
 opening, based on the reminder of the offer, a mobile application on the computing device; and 
 causing the offer to be presented on the computing device. 
 
     
     
       15. A computing device comprising:
 one or more processors; and 
 memory storing instructions that, when executed by the one or more processors, cause the computing device to:
 obtain a document; 
 identify, based on an automated analysis of the document, an anchor field; 
 identify, based on the automated analysis of the document, a second field based on the second field being within a threshold distance of the anchor field, wherein the second field comprises time-sensitive information; 
 extract and store a plurality of details from the second field, wherein the plurality of details comprises an expiration date associated with the time-sensitive information; 
 determine, using a radiodetermination mechanism, a location of the computing device; and 
 send, based on a determination that the location of the computing device is associated with a merchant and based on a determination that the time-sensitive information has not expired, a reminder of an offer associated with the time-sensitive information. 
 
 
     
     
       16. The computing device of  claim 15 , wherein the second field comprises at least one of a barcode or a QR code. 
     
     
       17. The computing device of  claim 15 , wherein the threshold distance comprises a predetermined number of pixels. 
     
     
       18. The computing device of  claim 16 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
 train a machine learning model to recognize a plurality of documents, wherein each of the plurality of documents is associated with a merchant; and 
 use the machine learning model to further identify the anchor field and the second field. 
 
     
     
       19. The computing device of  claim 18 , wherein the plurailty of documents comprises at least one of:
 a receipt; 
 a proof of purchase; or 
 an invoice. 
 
     
     
       20. The computing device of  claim 16 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
 identify a plurality of fields; 
 extract one or more purchases from the plurality of fields; 
 categorize each of the one or more purchases; 
 generate an expenditure report indicative of a user's spending habits, wherein the expenditure report comprises a category for each of the one or more purchases; and 
 cause the expenditure report to be presented on the computing device.